Volume 12, Issue 47 (2015)                   FSCT 2015, 12(47): 141-157 | Back to browse issues page

XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Karimi S, Nikian A, Velayati A. Optimization of apple fruit sorter performance by detecting bruise and pedicle using machine vision technique. FSCT 2015; 12 (47) :141-157
URL: http://fsct.modares.ac.ir/article-7-3122-en.html
Abstract:   (4618 Views)
  Apple fruit is one of the most worthy garden Product with high nutritional Value and its production in Iran makes more job and Exchange technology. From different apple Non-destructive quality control methods, machine vision technology achieves the more speed, quality, greater productivity and higher valuation for the product. Usually, apple bruise overlaps with Peduncle and in these causes, serious problems of recognition for quality sorting occurs. In this research work it was tried to work out this problem and to increase the sorting systems performance precision. In order to accomplish this, two separate algorithms based on color to identify bruise and pedicle was designed in Matlab. It was achieved 97.14% accuracy for the bruise algorithm and 100% accuracy for the pedicle algorithm. Then with integration of these two algorithms, an algorithm was achieved with 94.29% accuracy. Further experiments to investigate the possibility of increasing the accuracy in detecting bruise with time maintenance was performed by the bruise algorithm. The results indicate that the bruise detection quality by this algorithm gradually increased and after two to three days it reaches the desired consistency. Another algorithm with special properties of bruise and pedicle pictures shape such as roundness value, ratio of area to Perimeter square and also coefficient of variation (cv) of distances of spaced points on the edge from center of gravity of picture was designed. Then bruise and pedicle were distinguished from each other with an accuracy of 100% with this algorithm along with the ANN which it proving the importance of using these techniques, combined with machine vision techniques to increase the accuracy of sorting machines performance.  
Full-Text [PDF 1049 kb]   (2598 Downloads)    

Received: 2014/05/21 | Accepted: 2015/02/20 | Published: 2015/07/23

Add your comments about this article : Your username or Email:
CAPTCHA

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.